Step 3.5 Flash
TL;DR
Open-sourceFast open-source sparse-MoE agentic reasoning with a 1M context.
Available on
Open-source models are available on every plan, including Go ($1/mo).
Switch with
Pick Step 3.5 Flash from the selector.
Intelligence Index
Step 3.5 Flash vs the top of the lineup
Claude Fable 5
GPT-5.6 Sol
Claude Opus 4.8
Step 3.5 Flash
Speed
~207
tokens / sec
Input
$0.10
per M tokens
Output
$0.30
per M tokens
Step 3.5 Flash in Command Code
Step 3.5 Flash is StepFun's open-source model — fast sparse-MoE agentic reasoning. It runs in Command Code with a 1M-token context window, switchable any time with /model.
It scores 26 on the Intelligence Index — #36 of the 38 scored models in the Command Code lineup.
Step 3.5 Flash specs at a glance
What Step 3.5 Flash accepts, how much it can hold in context, and what you need to run it.
| Spec | Step 3.5 Flash |
|---|---|
| Context window | 1M tokens |
| Input modalities | text |
| Reasoning | Yes |
| Release date | 2026-04-02 |
| Minimum plan | Go |
Step 3.5 Flash vs the Command Code lineup
Step 3.5 Flash alongside its nearest real alternatives in the lineup — every price straight from the billing tables.
| Model | Intelligence | Coding | Speed | Input $/M | Output $/M | Blended $/M | Context |
|---|---|---|---|---|---|---|---|
| Claude Fable 5 | 59.9 | 76.5 | ~62 tok/s | $10.00 | $50.00 | $20 | 1M |
| Tencent Hy3 | 41.2 | 58.8 | ~58 tok/s | $0.00 | $0.00 | free | 262K |
| MiniMax M2.5 | 33.7 | — | ~78 tok/s | $0.30 | $1.20 | $0.525 | 200K |
| Step 3.7 Flash | 30.3 | 39.6 | ~407 tok/s | $0.20 | $1.15 | $0.4375 | 256K |
| Step 3.5 Flash (this page) | 26 | — | ~207 tok/s | $0.10 | $0.30 | $0.15 | 1M |
| Gemini 3.1 Flash Lite | 25 | 34.7 | ~300 tok/s | $0.25 | $1.50 | $0.5625 | 1M |
| Claude Haiku 4.5 | 23.7 | — | ~103 tok/s | $1.00 | $5.00 | $2 | 200K |
What Step 3.5 Flash is best for
Step 3.5 Flash is a open-source model from StepFun, cheaper blended than most of the lineup ($0.15 per million tokens). It streams fast enough for interactive lookups.
The honest way to place it: run your own session with /model and compare against the lineup table above — the numbers on this page update as the registry and billing tables change.
When to switch away from Step 3.5 Flash
No single model wins every task. These are Step 3.5 Flash's computed nearest alternatives — one step up, one step down in cost, one for speed, one from the same family — each switchable mid-session with /model.
Switch to Step 3.7 Flash
Step 3.7 Flash scores 30.3 on the Intelligence Index to Step 3.5 Flash's 26 — the nearest genuine step up — at $0.4375 blended per million tokens versus $0.15. Reach for it when a task keeps hitting Step 3.5 Flash's ceiling.
Switch to Tencent Hy3
Tencent Hy3 runs about 100% cheaper blended (free versus $0.15 per million tokens) while scoring 41.2 on the Intelligence Index. Switch down for high-volume work where Step 3.5 Flash's edge isn't earning its rate.
Switch to Gemini 3.1 Flash Lite
Gemini 3.1 Flash Lite streams ~300 tokens/sec to Step 3.5 Flash's ~207 at a comparable blended cost ($0.5625 per million tokens). Use it when iteration speed matters more than squeezing out the last point of quality.
What you pay for Step 3.5 Flash
Step 3.5 Flash is billed per token at the rates below — the same billing tables the Usage page charges against, so this page cannot quote a different price than you pay.
Blended cost (3:1 input:output, the shape of a typical coding session) works out to $0.15 per million tokens.
| Per 1M tokens | Input | Output | Cache read |
|---|---|---|---|
| All requests | $0.10 | $0.30 | $0.02 |
In Command Code: caching and taste-1
Open-source models are routed across multiple upstream providers for high availability. The price you see is the mean per-provider rate; the Usage page reflects what was actually charged.
Where supported by the upstream, prompt caching is on by default — cache reads are billed at $0.02 per million tokens versus $0.10 for fresh input.
taste-1 sits between the model and the agent loop, rewriting and reranking candidate edits to match your codebase conventions.
Plan availability
Step 3.5 Flash is an open-source model, available on every plan including Go.
Command Code is a subscription with model usage at API rates. Each plan ships with monthly LLM credits; credits roll over and never expire, and auto top-up keeps you running if you go over.
| Plan | Price/mo | LLM credits | Models |
|---|---|---|---|
| Go | $1 | $10 | Open-source only |
| Pro | $15 | $30 | Open-source + premium |
| Provider | $15 | Pay as you go | Open-source + premium |
| Max 10× | $100 | $150 | Open-source + premium |
| Max 20× | $200 | $300 | Open-source + premium |
| Teams Pro | $40 / seat | $40 / seat | Open-source + premium |
| Enterprise | Custom | Custom | Custom pool, SSO, audit logs |
Switching models with /model
In an interactive Command Code session, run /model to open the model selector. Pick Step 3.5 Flash and it applies to this session and to future sessions until you change it again. Premium models require Pro or higher; open-source models are available on every plan, including Go.
cmd # start an interactive session
/model # open the selector and pick Step 3.5 FlashAll Command Code models, ranked by quality and speed
Quality is the Intelligence Index — an aggregate score across reasoning, math, coding, and knowledge evaluations. Speed is measured output tokens per second. Models without a published score are noted. This table is regenerated from the model registry, so it is always current.
| Model | Tier | Intelligence Index | Output speed |
|---|---|---|---|
| Claude Fable 5 | Premium | 59.9 | ~62 tok/s |
| GPT-5.6 Sol | Premium | 58.9 | ~77 tok/s |
| Claude Opus 4.8 | Premium | 55.7 | ~55 tok/s |
| GPT-5.6 Terra | Premium | 55 | ~155 tok/s |
| GPT-5.5 | Premium | 54.8 | ~81 tok/s |
| Grok 4.5 | Open-source | 53.8 | ~114 tok/s |
| Claude Opus 4.7 | Premium | 53.5 | ~52 tok/s |
| Claude Sonnet 5 | Premium | 53.4 | ~79 tok/s |
| GPT-5.4 | Premium | 51.4 | ~164 tok/s |
| GPT-5.6 Luna | Premium | 51.2 | ~234 tok/s |
| GLM-5.2 | Open-source | 51.1 | ~208 tok/s |
| Muse Spark 1.1 | Premium | 50.6 | ~130 tok/s |
| Gemini 3.5 Flash | Premium | 50.2 | ~236 tok/s |
| Claude Sonnet 4.6 | Premium | 47.2 | ~55 tok/s |
| Qwen 3.7 Max | Open-source | 46 | ~196 tok/s |
| MiniMax M3 | Open-source | 44.4 | ~113 tok/s |
| DeepSeek V4 Pro | Open-source | 44.3 | ~62 tok/s |
| GPT-5.3 Codex | Premium | 44.3 | ~106 tok/s |
| Kimi K2.6 | Open-source | 44.2 | ~43 tok/s |
| MiMo V2.5 Pro | Open-source | 42.2 | ~56 tok/s |
| Kimi K2.7 Code | Open-source | 41.9 | ~46 tok/s |
| Tencent Hy3 | Open-source | 41.2 | ~58 tok/s |
| DeepSeek V4 Flash | Open-source | 40.3 | ~106 tok/s |
| GLM-5.1 | Open-source | 40.2 | ~81 tok/s |
| Qwen 3.6 Max Preview | Open-source | 40 | ~46 tok/s |
| GPT-5.4 Mini | Premium | 40 | ~171 tok/s |
| Qwen 3.6 Plus | Open-source | 39.6 | ~53 tok/s |
| GLM-5 | Open-source | 39.5 | ~51 tok/s |
| Qwen 3.7 Plus | Open-source | 39 | ~52 tok/s |
| Kimi K2.5 | Open-source | 38.1 | ~51 tok/s |
| MiniMax M2.7 | Open-source | 38.1 | ~49 tok/s |
| Nemotron 3 Ultra | Open-source | 37.8 | ~204 tok/s |
| MiMo V2.5 | Open-source | 37.2 | ~88 tok/s |
| MiniMax M2.5 | Open-source | 33.7 | ~78 tok/s |
| Step 3.7 Flash | Open-source | 30.3 | ~407 tok/s |
| Step 3.5 Flash (this page) | Open-source | 26 | ~207 tok/s |
| Gemini 3.1 Flash Lite | Premium | 25 | ~300 tok/s |
| Claude Haiku 4.5 | Premium | 23.7 | ~103 tok/s |
| Kimi K3 | Open-source | Not yet scored | — |
| Kimi K2.7 Code HighSpeed | Open-source | Not yet scored | — |
| GLM-5.2 Fast | Open-source | Not yet scored | — |
| Inkling | Open-source | Not yet scored | — |
| Fugu Ultra | Premium | Not yet scored | — |
Frequently asked questions
Step 3.5 Flash or Step 3.7 Flash?
Step 3.7 Flash scores higher on the Intelligence Index (30.3 vs 26) at $0.4375 blended per million tokens against Step 3.5 Flash's $0.15. Default to Step 3.5 Flash and switch up when a task keeps stalling.
Step 3.5 Flash or Tencent Hy3?
Tencent Hy3 is about 100% cheaper blended (free vs $0.15 per million tokens), scoring 41.2 on the Intelligence Index. Use Tencent Hy3 for volume work and Step 3.5 Flash where its edge earns the difference.
How much does Step 3.5 Flash cost in Command Code?
$0.10 per million input tokens and $0.30 per million output tokens, with cache reads at $0.02. In an agent loop, cached context brings effective input to roughly $0.044 per million tokens.
What plan do I need for Step 3.5 Flash?
Step 3.5 Flash is available on every plan, including Go at $1/mo.
Does Step 3.5 Flash support image input and reasoning?
Step 3.5 Flash is text-only; paste code and logs rather than screenshots. It supports reasoning.
Which Command Code model should I use?
Claude Fable 5 currently leads the lineup on the Intelligence Index (59.9). Grok 4.5 (53.8) leads the open-weights tier, available on every plan. For fast lookups, Step 3.7 Flash streams ~407 tok/s. There is no single right answer — switch per session with /model and let the task pick the model.
Can I mix Step 3.5 Flash with other models in a workflow?
Yes. Switch per session using /model. Common pattern: keep a default model and switch up for hard problems or down for quick lookups as the task calls for it.
Are open-source model prices fixed?
Open-source models are routed across multiple upstream providers for high availability. The price listed for each is the mean per-provider rate. Actual cost on a given request may vary slightly. The Usage page reflects the price charged.
Is Step 3.5 Flash too cheap to be useful?
For fast, narrow reasoning at scale, no — it pairs a sparse-MoE design with a 1M context. For multimodal work or stronger reasoning, switch to Step 3.7 Flash.
How is Step 3.5 Flash routed?
Through OpenRouter across multiple upstream providers (parasail, deepinfra, siliconflow). The listed price is the mean per-provider rate; the Usage page shows the actual charge.
Is Command Code free to try?
The Go plan starts at $1/mo with $10 in LLM credits. It covers open-source models only. Pro at $15/mo unlocks premium models with $30 in LLM credits.
Does Command Code train on my code?
No. Command Code does not train on your code or store your code snippets. taste-1 data is stored locally in your project directory.
Where can I track my usage?
The Usage page in Studio shows per-request cost, token counts, and which model ran. Settings > Billing lets you change plans, buy credits, or enable auto top-up.
Does Command Code replace my editor?
No. Command Code is editor-agnostic — it runs as a CLI and works alongside any editor (Cursor, VS Code, Zed, JetBrains, Neovim, etc.).
Related reading
- Step 3.7 Flash in Command Codemultimodal sparse-MoE reasoning
- Gemini 3.1 Flash Lite in Command Codehigh-volume workhorse model with implicit caching
- Claude Haiku 4.5 in Command Codefastest & most compact, great for quick tasks
- Every model, one referenceThe docs list of all Command Code models with ids and context windows.
- Pricing, limits, and dealsThe canonical price table, running deals, and usage estimates.
Ship code that matches your taste
Command Code is the AI coding agent that continuously learns your taste. Start for $1.